© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10777
    Prev
    Next
    INDEX
    Explanations

    sentences about dealing with computers or devices

    oai_token-act-pair · gemini-2.0-flash

    phone

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rispar
    -0.50
    зулта
    -0.49
     commerciali
    -0.48
    Vidite
    -0.46
     intercession
    -0.45
    Stored
    -0.45
    óri
    -0.44
    Bo
    -0.43
     négociations
    -0.43
    UnknownFields
    -0.42
    POSITIVE LOGITS
     phone
    0.96
     Phone
    0.87
     phones
    0.79
     iPhone
    0.79
    AndEndTag
    0.78
     MacBook
    0.77
     PHONE
    0.75
     Phones
    0.74
     PC
    0.73
     smartphone
    0.71
    Activations Density 7.972%

    No Known Activations